© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 253508
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zka
    0.51
    قابل
    0.48
    ೋಜನ
    0.47
    وبا
    0.47
    ванням
    0.47
     從
    0.47
    ਕ
    0.47
    ਆਂ
    0.46
    മാണ്
    0.44
     Salaries
    0.44
    POSITIVE LOGITS
     lực
    0.51
     addSubview
    0.50
     оли
    0.48
     службу
    0.47
     pum
    0.46
     সেদিন
    0.45
     besar
    0.44
     dừng
    0.43
    本当
    0.43
     hỗn
    0.43
    Activations Density 0.001%

    No Known Activations